Method and apparatus for displaying face of virtual role, computer device, and readable storage medium

1. A method for displaying a face of a virtual role, the method comprising:

obtaining, by a device comprising a memory storing instructions and a processor in communication with the memory, a face parameter corresponding to a user face, the face parameter being used for indicating a facial feature of a face region of the user face;

determining, by the device, a warping control parameter according to the face parameter, the warping control parameter being used for controlling a warping degree of a face region of a virtual role, by:

obtaining, by the device, a parameter mapping relationship indicating a correspondence between the face parameter and the warping control parameter, and

determining, by the device, the warping control parameter corresponding to the face parameter according to the parameter mapping relationship;

generating, by the device, a virtual role face image according to the warping control parameter and a warping image set, the warping image set comprising a basic face image and at least one basic warping face image of the virtual role, and different basic warping face images corresponding to different face warping manners;

displaying, by the device, the virtual role face image; and

wherein:

the virtual role is a customized virtual role; and

the method further comprises:

generating, by the device, a sample virtual role face image according to a sample warping control parameter corresponding to the customized virtual role,

displaying, by the device, the sample virtual role face image in a face entry interface,

obtaining a sample face image, the sample face image being a face image acquired in a case that a user imitates the sample virtual role face image,

generating, by the device, a sample correspondence according to the sample warping control parameter and a sample face parameter corresponding to the sample face image, and

generating, by the device, the parameter mapping relationship according to the sample correspondence.

2. The method according to claim 1 , wherein the generating the virtual role face image according to the warping control parameter and the warping image set comprises:

determining, by the device, a target basic warping face image in the at least one basic warping face image according to the warping control parameter, the target basic warping face image and the warping control parameter being corresponding to a same face warping manner; and

generating, by the device, the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image.

3. The method according to claim 2 , wherein the generating the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image comprises:

determining, by the device, at least one interpolation ratio according to the warping control parameter, the at least one interpolation ratio comprising a first interpolation ratio corresponding to the basic face image and a second interpolation ratio corresponding to the target basic warping face image, and the at least one interpolation ratio being used for controlling an interpolation degree between the basic face image and the target basic warping face image; and

generating, by the device, the virtual role face image according to the basic face image, the first interpolation ratio, the target basic warping face image, and the second interpolation ratio.

4. The method according to claim 1 , wherein the obtaining the face parameter corresponding to the user face comprises:

acquiring, by the device with a camera, a face image of the user face in a target scenario; and

determining, by the device, the face parameter corresponding to the user face according to the face image.

5. The method according to claim 4 , wherein:

the camera is a depth camera;

the face image comprises depth data corresponding to each pixel; and

the determining the face parameter corresponding to the user face according to the face image comprises:

inputting, by the device, the face image to a face parameter prediction model, to obtain the face parameter outputted by the face parameter prediction model, the face parameter prediction model being a neural network model trained according to a sample face depth image and a sample face parameter corresponding to the sample face depth image.

6. An apparatus for displaying a face of a virtual role, the apparatus comprising:

a memory storing instructions;

a processor in communication with the memory, wherein, when the processor executes the instructions, the processor is configured to cause the apparatus to:

obtain a face parameter corresponding to a user face, the face parameter being used for indicating a facial feature of a face region of the user face,

determine a warping control parameter according to the face parameter, the warping control parameter being used for controlling a warping degree of a face region of a virtual role, by:

obtaining a parameter mapping relationship indicating a correspondence between the face parameter and the warping control parameter, and

determining the warping control parameter corresponding to the face parameter according to the parameter mapping relationship,

generate a virtual role face image according to the warping control parameter and a warping image set, the warping image set comprising a basic face image and at least one basic warping face image of the virtual role, and different basic warping face images corresponding to different face warping manners, and

display the virtual role face image; and

wherein:

the virtual role is a customized virtual role; and

when the processor executes the instructions, the processor is configured to further cause the apparatus to:

generate a sample virtual role face image according to a sample warping control parameter corresponding to the customized virtual role,

display the sample virtual role face image in a face entry interface,

obtain a sample face image, the sample face image being a face image acquired in a case that a user imitates the sample virtual role face image,

generate a sample correspondence according to the sample warping control parameter and a sample face parameter corresponding to the sample face image, and

generate the parameter mapping relationship according to the sample correspondence.

7. The apparatus according to claim 6 , wherein, when the processor is configured to cause the apparatus to generate the virtual role face image according to the warping control parameter and the warping image set, the processor is configured to cause the apparatus to:

determine a target basic warping face image in the at least one basic warping face image according to the warping control parameter, the target basic warping face image and the warping control parameter being corresponding to a same face warping manner; and

generate the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image.

8. The apparatus according to claim 7 , wherein, when the processor is configured to cause the apparatus to generate the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image, the processor is configured to cause the apparatus to:

determine at least one interpolation ratio according to the warping control parameter, the at least one interpolation ratio comprising a first interpolation ratio corresponding to the basic face image and a second interpolation ratio corresponding to the target basic warping face image, and the at least one interpolation ratio being used for controlling an interpolation degree between the basic face image and the target basic warping face image; and

generate the virtual role face image according to the basic face image, the first interpolation ratio, the target basic warping face image, and the second interpolation ratio.

9. The apparatus according to claim 6 , wherein, when the processor is configured to cause the apparatus to obtain the face parameter corresponding to the user face, the processor is configured to cause the apparatus to:

acquire, by a camera, a face image of the user face in a target scenario; and

determine the face parameter corresponding to the user face according to the face image.

10. The apparatus according to claim 9 , wherein:

the camera is a depth camera;

the face image comprises depth data corresponding to each pixel; and

when the processor is configured to cause the apparatus to determine the face parameter corresponding to the user face according to the face image, the processor is configured to cause the apparatus to:

input the face image to a face parameter prediction model, to obtain the face parameter outputted by the face parameter prediction model, the face parameter prediction model being a neural network model trained according to a sample face depth image and a sample face parameter corresponding to the sample face depth image.

11. A non-transitory computer-readable storage medium storing computer-readable instructions, wherein, the computer-readable instructions, when executed by a processor, are configured to cause the processor to perform:

obtaining a face parameter corresponding to a user face, the face parameter being used for indicating a facial feature of a face region of the user face;

determining a warping control parameter according to the face parameter, the warping control parameter being used for controlling a warping degree of a face region of a virtual role,

obtaining a parameter mapping relationship indicating a correspondence between the face parameter and the warping control parameter, and

determining the warping control parameter corresponding to the face parameter according to the parameter mapping relationship;

generating a virtual role face image according to the warping control parameter and a warping image set, the warping image set comprising a basic face image and at least one basic warping face image of the virtual role, and different basic warping face images corresponding to different face warping manners;

displaying the virtual role face image; and

wherein:

the virtual role is a customized virtual role; and

when the computer-readable instructions are executed by the processor, the computer-readable instructions are configured to further cause the processor to perform:

generating a sample virtual role face image according to a sample warping control parameter corresponding to the customized virtual role,

displaying the sample virtual role face image in a face entry interface,

obtaining a sample face image, the sample face image being a face image acquired in a case that a user imitates the sample virtual role face image,

generating a sample correspondence according to the sample warping control parameter and a sample face parameter corresponding to the sample face image, and

generating the parameter mapping relationship according to the sample correspondence.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein, when the computer-readable instructions are configured to cause the processor to perform generating the virtual role face image according to the warping control parameter and the warping image set, the computer-readable instructions are configured to cause the processor to perform:

determining a target basic warping face image in the at least one basic warping face image according to the warping control parameter, the target basic warping face image and the warping control parameter being corresponding to a same face warping manner; and

generating the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image.

13. The non-transitory computer-readable storage medium according to claim 12 , wherein, when the computer-readable instructions are configured to cause the processor to perform generating the virtual role face image according to the warping control parameter, the basic face image, and the target basic warping face image, the computer-readable instructions are configured to cause the processor to perform:

determining at least one interpolation ratio according to the warping control parameter, the at least one interpolation ratio comprising a first interpolation ratio corresponding to the basic face image and a second interpolation ratio corresponding to the target basic warping face image, and the at least one interpolation ratio being used for controlling an interpolation degree between the basic face image and the target basic warping face image; and

generating the virtual role face image according to the basic face image, the first interpolation ratio, the target basic warping face image, and the second interpolation ratio.

14. The non-transitory computer-readable storage medium according to claim 11 , wherein, when the computer-readable instructions are configured to cause the processor to perform obtaining the face parameter corresponding to the user face, the computer-readable instructions are configured to cause the processor to perform:

acquiring, by a camera, a face image of the user face in a target scenario; and

determining the face parameter corresponding to the user face according to the face image.